{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,2]],"date-time":"2024-06-02T22:10:32Z","timestamp":1717366232688},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2010,7,1]],"date-time":"2010-07-01T00:00:00Z","timestamp":1277942400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["New Gener. Comput."],"published-print":{"date-parts":[[2010,7]]},"DOI":"10.1007\/s00354-009-0091-y","type":"journal-article","created":{"date-parts":[[2010,8,13]],"date-time":"2010-08-13T13:45:15Z","timestamp":1281707115000},"page":"299-319","source":"Crossref","is-referenced-by-count":17,"title":["Speech Structure and Its Application to Robust Speech Processing"],"prefix":"10.1007","volume":"28","author":[{"given":"Nobuaki","family":"Minematsu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Asakawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masayuki","family":"Suzuki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,8,14]]},"reference":[{"key":"91_CR1","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1038\/nrn1533","volume":"5","author":"P.K. Kuhl","year":"2004","unstructured":"Kuhl, P. K., \u201cEarly language acquisition: Cracking the speech code,\u201d Nature Reviews Neuroscience, 5, pp.831\u2013843, 2004.","journal-title":"Nature Reviews Neuroscience"},{"key":"91_CR2","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1016\/j.specom.2007.02.006","volume":"49","author":"M. Benzeghiba","year":"2007","unstructured":"Benzeghiba, M., De Mori, R., Deroo, O., Dupont, S., Erbes, T., Jouvet, D., Fissore, L., Laface, P., Mertins, A., Ris, C., Rose, R., Tyagi, V. and Wellekens, C., \u201cAutomatic speech recognition and speech variability: A review,\u201d Speech Communication, 49, pp.763\u2013786, 2007.","journal-title":"Speech Communication"},{"key":"91_CR3","doi-asserted-by":"crossref","unstructured":"Lotto, R. B. and Purves, D., \u201cAn empirical explanation of color contrast,\u201d in Proc. the National Academy of Science USA, 97, pp.12834\u201312839, 2000.","DOI":"10.1073\/pnas.210369597"},{"issue":"11","key":"91_CR4","doi-asserted-by":"crossref","first-page":"1010","DOI":"10.1038\/14808","volume":"2","author":"R.B. Lotto","year":"1999","unstructured":"Lotto, R. B. and Purves, D., \u201cThe effects of color on brightness,\u201d Nature neuroscience, 2, 11, pp.1010\u20131014, 1999.","journal-title":"Nature neuroscience"},{"key":"91_CR5","unstructured":"Taniguchi, T., Sounds become music in mind -introduction to music psychology-, Kitaoji Pub., 2000."},{"key":"91_CR6","unstructured":"http:\/\/www.lottolab.org\/illusiondemos\/Demo%2012.html"},{"key":"91_CR7","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1146\/annurev.ento.46.1.471","volume":"46","author":"A.D. Briscoe","year":"2001","unstructured":"Briscoe, A. D. and Chittka, L., \u201cThe evolution of color vision in insects,\u201d Annual review of entomology, 46, pp.471\u2013510, 2001.","journal-title":"Annual review of entomology"},{"key":"91_CR8","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1038\/nn1080","volume":"6","author":"M.D. Hauser","year":"2003","unstructured":"Hauser, M. D. and McDermott, J., \u201cThe evolution of the music faculty: a comparative perspective,\u201d Nature neurosciences, 6, pp.663\u2013668, 2003.","journal-title":"Nature neurosciences"},{"key":"91_CR9","unstructured":"Acquisition of Communication and Recognition Skills Project (ACORNS). http:\/\/www.acorns-project.org\/"},{"key":"91_CR10","unstructured":"Human Speechome Project, http:\/\/www.media.mit.edu\/press\/speechome\/"},{"key":"91_CR11","unstructured":"Infants' Commonsense Knowledge Project, http:\/\/minny.cs.inf.shizuoka.ac.jp\/SIG-ICK\/"},{"key":"91_CR12","unstructured":"Kato, M., \u201cPhonological development and its disorders,\u201d Journal of Communication Disorders, 20, 2, pp.84\u201385, 2003."},{"key":"91_CR13","doi-asserted-by":"crossref","unstructured":"Shaywitz, S. E., Overcoming dyslexia, Random House, 2005.","DOI":"10.3109\/9780203090442-6"},{"key":"91_CR14","unstructured":"Hayakawa, M., \u201cLanguage acquisition and matherese,\u201d Language, 35, 9, Taishukan pub., pp.62\u201367, 2006."},{"key":"91_CR15","doi-asserted-by":"crossref","unstructured":"Lieberman, P., \u201cOn the development of vowel production in young children,\u201d Child Phonology vol.1, (Yeni-Komshian, G. H., Kavanagh, J. F. and Ferguson, C. A. eds.), Academic Press, 1980.","DOI":"10.1016\/B978-0-12-770601-6.50012-7"},{"key":"91_CR16","unstructured":"Okanoya, K., \u201cBirdsongs and human language: common evolutionary mechanisms,\u201d in Proc. Spring Meet. Acoust. Soc. Jpn., 1-17-5, pp.1555\u20131556, 2008 (including Q&A after his presentation)."},{"key":"91_CR17","unstructured":"Gruhn, W., \u201cThe audio-vocal system in sound perception and learning of language and music,\u201d in Proc. Int. Conf. on language and music as cognitive systems, 2006."},{"issue":"1","key":"91_CR18","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1109\/89.736329","volume":"7","author":"S. Umesh","year":"1999","unstructured":"Umesh, S., Cohen, L., Marinovic, N. and Nelson, D. J., \u201cScale transform in speech analysis,\u201d IEEE Trans. Speech and Audio Processing, 7, 1, pp.40\u201345, 1999.","journal-title":"Speech and Audio Processing"},{"key":"91_CR19","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/S0167-6393(00)00085-6","volume":"36","author":"T. Irino","year":"2002","unstructured":"Irino, T. and Patterson, R. D., \u201cSegregating information about the size and shape of the vocal tract using a time-domain auditory model: the stabilised wavelet-Mellin transform\u201d, Speech Communication, 36, pp.181\u2013203, 2002.","journal-title":"Speech Communication"},{"key":"91_CR20","doi-asserted-by":"crossref","unstructured":"Mertins, A. and Rademacher, J., \u201cVocal trace length invariant features for automatic speech recognition,\u201d in Proc. IEEE Workshop on Automatic Speech Recognition and Understanding, pp.308\u2013312, 2005.","DOI":"10.1109\/ASRU.2005.1566473"},{"key":"91_CR21","unstructured":"Jakobson, R. and Waugh, L. R., The sound shape of language, Mouton De Gruyter, 1987."},{"issue":"1","key":"91_CR22","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1121\/1.1908694","volume":"29","author":"P. Ladefoged","year":"1957","unstructured":"Ladefoged, P. and Broadbent, D. E., \u201cInformation conveyed by vowels,\u201d Journal of Acoust. Soc. Am., 29, 1, pp.98\u2013104, 1957.","journal-title":"Journal of Acoust. Soc. Am."},{"issue":"5","key":"91_CR23","doi-asserted-by":"crossref","first-page":"2088","DOI":"10.1121\/1.397861","volume":"85","author":"T.M. Nearey","year":"1989","unstructured":"Nearey, T. M., \u201cStatic, dynamic, and relational properties in vowel perception,\u201d Journal of Acoust. Soc. Am., 85, 5, pp.2088\u20132113, 1989.","journal-title":"Journal of Acoust. Soc. Am."},{"key":"91_CR24","unstructured":"Hawkins, J. and Blakeslee, S., On intelligence, Henry Holt, 2004."},{"issue":"7","key":"91_CR25","doi-asserted-by":"crossref","first-page":"3884","DOI":"10.1109\/TSP.2010.2047340","volume":"58","author":"Y. Qiao","year":"2010","unstructured":"Qiao, Y. and Minematsu, N., \u201cA study on invariance of f-divergence and its application to speech recognition,\u201d IEEE Transactions on Signal Processing, 58, 7, pp.3884\u20133890, 2010.","journal-title":"IEEE Transactions on Signal Processing"},{"key":"91_CR26","first-page":"299","volume":"2","author":"I. Csiszar","year":"1967","unstructured":"Csiszar, I., \u201cInformation-type measures of difference of probability distributions and indirect,\u201d Stud. Sci. Math. Hung., 2, pp.299\u2013318, 1967.","journal-title":"Stud. Sci. Math. Hung"},{"key":"91_CR27","doi-asserted-by":"crossref","unstructured":"Minematsu, N., \u201cMathematical evidence of the acoustic universal structure in speech,\u201d in Proc. Int. Conf. Acoustics, Speech, & Signal Processing, pp.889\u2013892, 2005.","DOI":"10.1109\/ICASSP.2005.1415257"},{"key":"91_CR28","unstructured":"Minematsu, N., Nishimura, T., Nishinari, K. and Sakuraba, K., \u201cTheorem of the invariant structure and its derivation of speech Gestalt,\u201d in Proc. Int. Workshop on Speech Recognition and Intrinsic Variations, pp.47\u201352, 2006."},{"key":"91_CR29","unstructured":"Minematsu, N., \u201cPronunciation assessment based upon the phonological distortions observed in language learners' utterances,\u201d in Proc. Int. Conf. Spoken Language Processing, pp.1669\u20131672, 2004."},{"key":"91_CR30","doi-asserted-by":"crossref","unstructured":"Saito, D., Matsuura, R., Asakawa, S., Minematsu, N. and Hirose, K., \u201cDirectional dependency of cepstrum on vocal tract length,\u201d in Proc. Int. Conf. Acoustics, Speech, & Signal Processing, pp.4485\u20134488, 2008.","DOI":"10.1109\/ICASSP.2008.4518652"},{"issue":"5","key":"91_CR31","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1089\/106652701446152","volume":"7","author":"I. Edihammer","year":"2000","unstructured":"Edihammer, I., \u201cStructure comparison and structure patterns,\u201d Journal of Computational Biology, 7, 5, pp.685\u2013716, 2000.","journal-title":"Journal of Computational Biology"},{"issue":"5","key":"91_CR32","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1109\/TSA.2005.848881","volume":"13","author":"M. Pitz","year":"2005","unstructured":"Pitz, M. and Ney, H., \u201cVocal tract normalization equals linear transformation in cepstral space,\u201d IEEE Trans. Speech and Audio Processing, 13, 5, pp.930\u2013944, 2005.","journal-title":"IEEE Trans. Speech and Audio Processing"},{"key":"91_CR33","unstructured":"Emori, T. and Shinoda, K., \u201cRapid vocal tract length normalization using maximum likelihood estimation,\u201d in Proc. EUROSPEECH, pp.1649\u20131652, 2001."},{"key":"91_CR34","unstructured":"Naito, M., Deng, L. and Sagisaka, Y., \u201cModel based speaker normalization methods for speech recognition,\u201d IEICE Trans. J83-D-II, 11, pp.2360\u20132369, 2000."},{"key":"91_CR35","unstructured":"Tohoku university - Matsushita isolated Word database (TMW), http:\/\/research.nii.ac.jp\/src\/eng\/list\/detail.html# TMW"},{"key":"91_CR36","unstructured":"Kawahara, T., Lee, A., Takeda, K., Itou, K. and Shikano, K., \u201cRecent progress of open-source LVCSR engine Julius and Japanese model repository,\u201d in Proc. Int. Conf. on Spoken Language Processing, pp.3069\u20133072, 2004."},{"key":"91_CR37","doi-asserted-by":"crossref","unstructured":"Qiao, Y., Suzuki, M. and Minematsu, N., \u201cA study of Hidden Structure Model and its application of labeling sequences,\u201d in Proc. IEEE Workshop on Automatic Speech Recognition and Understanding, pp.118\u2013123, 2009.","DOI":"10.1109\/ASRU.2009.5373239"},{"key":"91_CR38","doi-asserted-by":"crossref","unstructured":"Greenberg, S. and Kingsbury, B., \u201cThe modulation spectrogram: in pursuit of an invariant representation of speech,\u201d in Proc. Int. Conf. Acoustics, Speech, & Signal Processing, pp.1647\u20131650, 1997.","DOI":"10.1109\/ICASSP.1997.598826"},{"issue":"4","key":"91_CR39","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1109\/89.326616","volume":"2","author":"H. Hermansky","year":"1994","unstructured":"Hermansky, H. and Morgan, N., \u201cRASTA processing of speech,\u201d IEEE Trans. Speech and Audio Processing, 2, 4, pp.578\u2013589, 1994.","journal-title":"Speech and Audio Processing"},{"issue":"10","key":"91_CR40","doi-asserted-by":"crossref","first-page":"832","DOI":"10.1016\/j.specom.2009.04.005","volume":"51","author":"M. Eskenazi","year":"2009","unstructured":"Eskenazi, M., \u201cAn overview of spoken language technology for education,\u201d Speech Communication, 51, 10, pp.832\u2013844, 2009.","journal-title":"Speech Communication"},{"key":"91_CR41","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/S0167-6393(99)00044-8","volume":"30","author":"S.M. Witt","year":"2000","unstructured":"Witt, S. M. and Young, S. J., \u201cPhone-level pronunciation scoring and assessment for interactive language learning,\u201d Speech Communication, 30, pp.95\u2013108, 2000.","journal-title":"Speech Communication"},{"key":"91_CR42","doi-asserted-by":"crossref","unstructured":"Minematsu, N., Asakawa, S. and Hirose, K., \u201cStructural representation of the pronunciation and its use for CALL,\u201d in Proc. IEEE Int. Workshop on Spoken Language Technology, pp.126\u2013129, 2006.","DOI":"10.1109\/SLT.2006.326833"},{"key":"91_CR43","unstructured":"Minematsu, N., \u201cTraining of pronunciation as learning of the sound system embedded in the target language,\u201d in Proc. Int. Symposium on Phonetic Frontiers, CD-ROM, 2008."},{"key":"91_CR44","unstructured":"Minematsu, N., et al., \u201cDevelopment of English speech database read by Japanese to support CALL research,\u201d in Proc. Int. Conf. Acoustics, pp.577\u2013560, 2004."},{"key":"91_CR45","unstructured":"Frith, U., Autism: explaining the enigma, Wiley-Blackwell, 2003."},{"key":"91_CR46","unstructured":"Willey, L. H. and Attwood, T., Pretending to be normal: living with Asperger's syndrome, Jessica Kingsley Publishers, 1999."},{"key":"91_CR47","unstructured":"Grandin, T. and Johnson, C., Animals in translation: using the mysteries of autism to decode animal behavior, Scribner, 2004."},{"key":"91_CR48","unstructured":"Higashida, N. and Higashida, M., Messages to all my colleagues living on the planet, Escor Pub., Chiba, 2005."}],"container-title":["New Generation Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00354-009-0091-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00354-009-0091-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00354-009-0091-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T16:31:42Z","timestamp":1559406702000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00354-009-0091-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,7]]},"references-count":48,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2010,7]]}},"alternative-id":["91"],"URL":"https:\/\/doi.org\/10.1007\/s00354-009-0091-y","relation":{},"ISSN":["0288-3635","1882-7055"],"issn-type":[{"value":"0288-3635","type":"print"},{"value":"1882-7055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,7]]}}}